gwaslab 3.5.4__tar.gz → 3.5.6__tar.gz

{gwaslab-3.5.4/src/gwaslab.egg-info → gwaslab-3.5.6}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: gwaslab
-Version: 3.5.4
+Version: 3.5.6
 Summary: A collection of handy tools for GWAS SumStats
 Author-email: Yunye <yunye@gwaslab.com>
 Project-URL: Homepage, https://cloufield.github.io/gwaslab/
@@ -14,7 +14,7 @@ License-File: LICENSE
 License-File: LICENSE_before_v3.4.39
 Requires-Dist: pandas!=1.5,>=1.3
 Requires-Dist: numpy<2,>=1.21.2
-Requires-Dist: matplotlib!=3.7.2,<3.9,>=3.5
+Requires-Dist: matplotlib<3.9,>=3.8
 Requires-Dist: seaborn>=0.12
 Requires-Dist: scipy>=1.12
 Requires-Dist: pySAM==0.22.1
@@ -51,7 +51,7 @@ Warning: Known issues of GWASLab are summarized in [https://cloufield.github.io/
 ### install via pip
 
 ```
-pip install gwaslab==3.5.0
+pip install gwaslab==3.5.4
 ```
 
 ```python

{gwaslab-3.5.4 → gwaslab-3.5.6}/README.md

@@ -23,7 +23,7 @@ Warning: Known issues of GWASLab are summarized in [https://cloufield.github.io/
 ### install via pip
 
 ```
-pip install gwaslab==3.5.0
+pip install gwaslab==3.5.4
 ```
 
 ```python

{gwaslab-3.5.4 → gwaslab-3.5.6}/pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "gwaslab"
-version = "3.5.4"
+version = "3.5.6"
 authors = [
   { name="Yunye", email="yunye@gwaslab.com" },
 ]
@@ -18,7 +18,7 @@ readme = "README.md"
 dependencies = [
     "pandas>=1.3,!=1.5",
     "numpy>=1.21.2,<2",
-    "matplotlib>=3.5,!=3.7.2,<3.9",
+    "matplotlib>=3.8,<3.9",
     "seaborn>=0.12",
     "scipy>=1.12",
     "pySAM==0.22.1",

{gwaslab-3.5.4 → gwaslab-3.5.6}/src/gwaslab/__init__.py

@@ -46,4 +46,6 @@ from gwaslab.util_ex_process_h5 import process_vcf_to_hfd5
 from gwaslab.util_ex_run_susie import _run_susie_rss as run_susie_rss
 from gwaslab.io_read_tabular import _read_tabular as read_tabular
 from gwaslab.util_in_meta import meta_analyze
-from gwaslab.viz_plot_scatter_with_reg import scatter
+from gwaslab.viz_plot_scatter_with_reg import scatter
+from gwaslab.util_in_fill_data import rank_based_int
+from gwaslab.g_SumstatsSet import SumstatsSet

{gwaslab-3.5.4 → gwaslab-3.5.6}/src/gwaslab/g_Sumstats.py

@@ -30,6 +30,7 @@ from gwaslab.hm_harmonize_sumstats import rsidtochrpos
 from gwaslab.hm_harmonize_sumstats import parallelizeassignrsid
 from gwaslab.hm_harmonize_sumstats import parallelinferstrand
 from gwaslab.hm_harmonize_sumstats import parallelrsidtochrpos
+from gwaslab.hm_harmonize_sumstats import _paralleleinferafwithmaf
 from gwaslab.util_in_filter_value import filtervalues
 from gwaslab.util_in_filter_value import filterout
 from gwaslab.util_in_filter_value import filterin
@@ -39,6 +40,7 @@ from gwaslab.util_in_filter_value import _filter_indel
 from gwaslab.util_in_filter_value import _filter_palindromic
 from gwaslab.util_in_filter_value import _filter_snp
 from gwaslab.util_in_filter_value import _exclude_hla
+from gwaslab.util_in_filter_value import _search_variants
 from gwaslab.util_in_filter_value import inferbuild
 from gwaslab.util_in_filter_value import sampling
 from gwaslab.util_in_filter_value import _get_flanking
@@ -77,9 +79,12 @@ from gwaslab.util_ex_ldsc import _estimate_h2_by_ldsc
 from gwaslab.util_ex_ldsc import _estimate_rg_by_ldsc
 from gwaslab.util_ex_ldsc import _estimate_h2_cts_by_ldsc
 from gwaslab.util_ex_ldsc import _estimate_partitioned_h2_by_ldsc 
+from gwaslab.util_ex_ldproxyfinder import _extract_ld_proxy
 from gwaslab.bd_get_hapmap3 import gethapmap3
 from gwaslab.util_abf_finemapping import abf_finemapping
 from gwaslab.util_abf_finemapping import make_cs
+from gwaslab.io_read_pipcs import _read_pipcs
+from gwaslab.viz_plot_credible_sets import _plot_cs
 import gc
 from gwaslab.viz_plot_phe_heatmap import _gwheatmap
 
@@ -88,6 +93,7 @@ class Sumstats():
     def __init__(self,
              sumstats,
              fmt=None,
+             tab_fmt="tsv",
              snpid=None,
              rsid=None,
              chrom=None,
@@ -154,10 +160,17 @@ class Sumstats():
         self.meta["gwaslab"]["species"] = species
         
         # initialize attributes for clumping and finmapping
-        self.to_finemapping_file_path = ""
-        self.to_finemapping_file  = pd.DataFrame()
-        self.plink_log = ""
-        self.clumps = pd.DataFrame()
+        #self.to_finemapping_file_path = ""
+        #self.to_finemapping_file  = pd.DataFrame()
+        #self.plink_log = ""
+
+        # path / file / plink_log
+        self.finemapping = dict()
+
+        # clumps / clumps_raw / plink_log
+        self.clumps = dict()
+        
+        #
         self.pipcs = pd.DataFrame()
 
         # print gwaslab version information
@@ -167,6 +180,7 @@ class Sumstats():
         self.data  = preformat(
           sumstats=sumstats,
           fmt=fmt,
+          tab_fmt = tab_fmt,
           snpid=snpid,
           rsid=rsid,
           chrom=chrom,
@@ -579,6 +593,24 @@ class Sumstats():
         else:
             self.data = _exclude_hla(self.data,log=self.log,**kwargs)
 
+    def search(self, inplace=False, **kwargs):
+        if inplace is False:
+            new_Sumstats_object = copy.deepcopy(self)
+            new_Sumstats_object.data = _search_variants(new_Sumstats_object.data,
+                                                        log=new_Sumstats_object.log,
+                                                        **kwargs)
+            return new_Sumstats_object
+        else:
+            self.data = _search_variants(self.data,log=self.log,**kwargs)
+    
+    def get_proxy(self,snplist, inplace=False, **kwargs):
+        if inplace is False:
+            new_Sumstats_object = copy.deepcopy(self)
+            new_Sumstats_object.data = _extract_ld_proxy(common_sumstats = new_Sumstats_object.data,
+                                                         snplist=snplist,
+                                                        log=new_Sumstats_object.log,
+                                                        **kwargs)
+            return new_Sumstats_object
 
     def random_variants(self,inplace=False,n=1,p=None,**kwargs):
         if inplace is True:
@@ -606,6 +638,11 @@ class Sumstats():
         self.data = paralleleinferaf(self.data,ref_infer=ref_infer,log=self.log,**kwargs)
         self.meta["gwaslab"]["references"]["ref_infer_af"] = ref_infer
         self.meta["gwaslab"]["references"]["ref_infer_af"] = _append_meta_record(self.meta["gwaslab"]["references"]["ref_infer_af"] , ref_infer)
+    def maf_to_eaf(self,ref_infer,**kwargs):
+        self.data = _paralleleinferafwithmaf(self.data,ref_infer=ref_infer,log=self.log,**kwargs)
+        self.meta["gwaslab"]["references"]["ref_infer_maf"] = ref_infer
+        self.meta["gwaslab"]["references"]["ref_infer_maf"] = _append_meta_record(self.meta["gwaslab"]["references"]["ref_infer_af"] , ref_infer)    
+    
     def plot_daf(self, **kwargs):
         fig,outliers = plotdaf(self.data, **kwargs)
         return fig, outliers
@@ -794,7 +831,7 @@ class Sumstats():
         credible_sets = make_cs(region_data,threshold=0.95,log=self.log)
         return region_data, credible_sets
     
-    
+
 ## LDSC ##############################################################################################
     def estimate_h2_by_ldsc(self, build=None, verbose=True, match_allele=True, how="right", **kwargs):
         if build is None:
@@ -822,21 +859,31 @@ class Sumstats():
 # external ################################################################################################
     
     def calculate_ld_matrix(self,**kwargs):
-        self.to_finemapping_file_path, self.to_finemapping_file, self.plink_log  = tofinemapping(self.data,study = self.meta["gwaslab"]["study_name"],**kwargs)
+        self.finemapping["path"],self.finemapping["file"],self.finemapping["plink_log"]= tofinemapping(self.data,study = self.meta["gwaslab"]["study_name"],**kwargs)
+        #self.to_finemapping_file_path, self.to_finemapping_file, self.plink_log  = tofinemapping(self.data,study = self.meta["gwaslab"]["study_name"],**kwargs)
     
     def run_susie_rss(self,**kwargs):
-        self.pipcs=_run_susie_rss(self.to_finemapping_file_path,**kwargs)
+        self.pipcs=_run_susie_rss(self.finemapping["path"],**kwargs)
+        #self.pipcs=_run_susie_rss(self.to_finemapping_file_path,**kwargs)
     
     def clump(self,**kwargs):
-        self.clumps,self.plink_log = _clump(self.data, log=self.log, study = self.meta["gwaslab"]["study_name"], **kwargs)
+        self.clumps["clumps"], self.clumps["clumps_raw"], self.clumps["plink_log"] = _clump(self.data, log=self.log, study = self.meta["gwaslab"]["study_name"], **kwargs)
 
     def calculate_prs(self,**kwargs):
         combined_results_summary = _calculate_prs(self.data, log=self.log, study = self.meta["gwaslab"]["study_name"], **kwargs)
         return combined_results_summary
-    
+
+# loading aux data
+    def read_pipcs(self,prefix,**kwargs):
+        self.pipcs = _read_pipcs(self.data[["SNPID","CHR","POS"]],prefix, **kwargs)
+
+    def plot_pipcs(self, region,**kwargs):
+        _plot_cs(self.pipcs, region, **kwargs)
 # to_format ###############################################################################################       
 
     def to_format(self, path, build=None, verbose=True, **kwargs):
         if build is None:
             build = self.meta["gwaslab"]["genome_build"]
         _to_format(self.data, path, log=self.log, verbose=verbose, meta=self.meta, build=build, **kwargs)
+
+ 

{gwaslab-3.5.4 → gwaslab-3.5.6}/src/gwaslab/g_SumstatsPair.py

@@ -23,6 +23,7 @@ from gwaslab.viz_plot_compare_af import  plotdaf
 from gwaslab.util_ex_run_2samplemr import _run_two_sample_mr
 from gwaslab.util_ex_run_clumping import _clump
 from gwaslab.util_ex_ldproxyfinder import _extract_with_ld_proxy
+from gwaslab.g_headers import _get_headers
 
 class SumstatsPair( ):
     def __init__(self, sumstatsObject1, sumstatsObject2, study=None, suffixes = ("_1","_2") ,verbose=True ):
@@ -35,6 +36,7 @@ class SumstatsPair( ):
             self.study_name = "{}_{}".format(sumstatsObject1.meta["gwaslab"]["study_name"], sumstatsObject2.meta["gwaslab"]["study_name"])
         else:
             self.study_name = "{}_{}".format("STUDY1", "STUDY2")
+        
         self.snp_info_cols = []
         self.stats_cols =[]
         self.stats_cols2 =[]
@@ -45,11 +47,13 @@ class SumstatsPair( ):
         self.colocalization=pd.DataFrame()
         self.sumstats1 = pd.DataFrame()
         self.sumstats2 = pd.DataFrame()
-        self.mr = {}
-        self.clumps ={}
+        
+        self.mr =dict()
+        self.clumps =dict()
         self.ns = None
-        self.to_finemapping_file_path = ""
-        self.plink_log = ""
+        self.finemapping = dict()
+        #self.to_finemapping_file_path = ""
+        #self.plink_log = ""
 
         self.log.write( "Start to create SumstatsPair object..." )
         
@@ -66,16 +70,17 @@ class SumstatsPair( ):
                                 verbose=verbose)
 
         for i in sumstatsObject1.data.columns:
-            if i in ["SNPID","rsID","CHR","POS","EA","NEA","STATUS"]:
+            if i in _get_headers(mode="info"):
+                # extract SNP info columns from sumstats1
                 self.snp_info_cols.append(i)
-            elif i in ["BETA","SE","P","MLOG10P","N","N_CASE","N_CONTROL","Z","T","F","OR","OR_95L","OR_95U","HR","HR_95L","HR_95U","MAF","EAF","BETA_95L","BETA_95U"]:
+            elif i in _get_headers(mode="stats"):
                 self.stats_cols.append(i)
             else:
                 self.other_cols.append(i)
         for i in sumstatsObject2.data.columns:
-            if i in ["SNPID","rsID","CHR","POS","EA","NEA","STATUS"]:
+            if i in _get_headers(mode="info"):
                 continue
-            elif i in ["BETA","SE","P","MLOG10P","N","N_CASE","N_CONTROL","Z","T","F","OR","OR_95L","OR_95U","HR","HR_95L","HR_95U","MAF","EAF","BETA_95L","BETA_95U"]:
+            elif i in _get_headers(mode="stats"):
                 self.stats_cols2.append(i)
             else:
                 self.other_cols2.append(i)           
@@ -136,14 +141,13 @@ class SumstatsPair( ):
 
 
     def clump(self,**kwargs):
-        self.clumps["clumps"], self.clumps["plink_log"] = _clump(self.data, log=self.log, p="P_1",mlog10p="MLOG10P_1", study = self.study_name, **kwargs)
+        self.clumps["clumps"],self.clumps["clumps_raw"],self.clumps["plink_log"] = _clump(self.data, log=self.log, p="P_1",mlog10p="MLOG10P_1", study = self.study_name, **kwargs)
 
     def to_coloc(self,**kwargs):
-        self.to_finemapping_file_path, output_file_list, self.plink_log = tofinemapping(self.data,study=self.study_name,suffixes=self.suffixes,log=self.log,**kwargs)
+        self.finemapping["path"],self.finemapping["file"],self.finemapping["plink_log"] = tofinemapping(self.data,study=self.study_name,suffixes=self.suffixes,log=self.log,**kwargs)
 
     def run_coloc_susie(self,**kwargs):
-
-        self.colocalization = _run_coloc_susie(self.to_finemapping_file_path,log=self.log,ncols=self.ns,**kwargs)
+        self.colocalization = _run_coloc_susie(self.finemapping["path"],log=self.log,ncols=self.ns,**kwargs)
 
     def run_two_sample_mr(self, clump=False, **kwargs):
         exposure1 = self.study_name.split("_")[0]